Skip to content
Preprint

OmniBrain-0: A Unified Agentic Model for Embodied Intelligence

Oct 2026 · 2 citations · 70 references
Computer Science

TL;DR

OmniBrain-0 is introduced, a lightweight unified embodied agent that coordinates manipulation and navigation through a shared high-level decision model, integrating task understanding, planning, progress tracking, and feedback-driven recovery.

Abstract

General-purpose embodied intelligence requires robots to coordinate diverse skills over long horizons, track task progress, and recover from failures. Specialist policies alone do not ensure task-level reliability, while powerful multimodal agents rely on costly reasoning and external experience that compact models struggle to reproduce. We introduce OmniBrain-0, a lightweight unified embodied agent that coordinates manipulation and navigation through a shared high-level decision model, integrating task understanding, planning, progress tracking, and feedback-driven recovery. Our progressive training framework combines embodied pretraining, domain-specialized agent distillation, and multi-teacher on-policy distillation (MOPD). It distills powerful teachers'interaction experience into manipulation and navigation experts, then consolidates their decision capabilities into OmniBrain-0. Unification therefore occurs within the learned decision model rather than only at the tool interface. We further introduce Rubric-Guided Recursive Self-Improvement (RSI), a data flywheel in which a Meta-Agent turns execution evidence into refined rubrics, step-level reminders, and verified trajectories for domain-expert updates before their reconsolidation into OmniBrain-0 through MOPD. We evaluate OmniBrain-0 on LIBERO-Pro, LIBERO-Plus, RoboCasa365, RoboTwin 2.0, and R2R-CE Val-Unseen, as well as multiple real-world manipulation tasks. OmniBrain-0 combines strong cross-domain task performance with substantially lower inference and execution overhead than its closed-source teacher, demonstrating efficient transfer and consolidation of embodied capabilities into a compact unified agent.

View source

Similar papers

Preprint Oct 2026

EmbodiedEvo: Self-Evolving Coding Agent For Physical Intelligence

EmbodiedEvo is a self-evolving coding agent that distills physical feedback into reusable code Skills and diagnostic Lessons that improves weaker executors and shows the largest gains on memory-dependent tasks and successful reuse of coordinated procedures.

Wen-Yi Li, Yi-Zhe Chi, You-Jie Zheng et al. · 6 citations · ⚡3
Preprint Nov 2026

Toward the Era of Agentic Embodied Intelligence

This work introduces A2-MEAS, an embodied multi-agent framework built around code as a scaling interface that combines corrective language, spatial evidence, execution history, and action proposals to support efficient embodied learning.

Chao Liang, Kevin Chen, Fen Y. Li et al. · 0 citations
#artificial intelligence Preprint Oct 2026

EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution

Robot foundation models provide strong visuomotor control, yet their performance can degrade when object positions or task instructions change. Further improvements often require post-training on substantial robot data, which can be costly to collect through methods such as teleoperation. Agentic harnesses can adapt ar...

Python Song, Zhi-Xuan Liang, Kelsey Fu et al. · 9 citations · ⚡1
Preprint Oct 2026

RoboBridge: A Self-Evolving Embodied Agent Framework for Sim-to-Real Transfer

The proposed RoboBridge framework provides a route from one-shot policy deployment to continual procedural learning across environments, and preserves reusable task structure while allowing environment-dependent operations to be selectively revised through real-world execution feedback.

Chen-Xi Li, Zhang-Rui Zhao, Rui Li et al. · 3 citations

UnifiedPlayers: Enhance Tool-Integrated Reasoning in Agentic Reinforcement Learning

UnifiedPlayers, a cooperative framework comprising a Planning Player that generates tasks, an Execution Player that produces multi-turn trajectories with Python tool calls, and an Evaluation Player that constructs executable verifiers, highlights cooperation among specialized players as a promising path toward self-enh...

Wen-Jie Liao, Liang Zhao, Ze-Hong Cao · 0 citations

EmbodiedEvo: Self-improving Coding Agents for Physical Intelligence

EmbodiedEvo is introduced, where a coding agent evolves reusable Skills and Lessons through feedback on a single Playground scene, then freezes the resulting harness for diverse new scenes, to retain and refine experience for later scenes.

Wen-Yi Li, Yi-Zhe Chi, You-Jie Zheng et al. · 1 citation · ⚡1

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.